{"id":"W4416157244","doi":"10.1109/trustcom66490.2025.00125","title":"Enhancing Adversarial Robustness of IoT Intrusion Detection via SHAP-Based Attribution Fingerprinting","year":2025,"lang":"en","type":"article","venue":"","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; University of Guelph; York University","funders":"National Research Council","keywords":"Adversarial system; Robustness (evolution); Intrusion detection system; Internet of Things; Evasion (ethics); Transparency (behavior); Attack model; Attribution","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009789094,0.0001969943,0.0002833919,0.0003848326,0.0003222438,0.00007344134,0.0006737874,0.00016983,0.00005414913],"category_scores_gemma":[0.0005133424,0.0002009278,0.0001198545,0.001155006,0.00005437254,0.000339872,0.0005313648,0.0003537042,0.000007086079],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002023256,"about_ca_system_score_gemma":0.0001639704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002151341,"about_ca_topic_score_gemma":0.00009027823,"domain_scores_codex":[0.9981058,0.0001938407,0.0005211064,0.0005078771,0.000342093,0.0003292586],"domain_scores_gemma":[0.9985977,0.0003351884,0.0002833362,0.0005016261,0.0002329857,0.00004911799],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007884686,0.00007291093,0.001221492,0.000122985,0.00002982225,0.000003032407,0.0001265039,0.6753991,0.1147649,0.008449615,0.00001375499,0.199717],"study_design_scores_gemma":[0.0005618017,0.00003857169,0.00182613,0.0001098472,0.00001482812,0.000001503341,0.00001918466,0.7883924,0.2084584,0.0002936376,0.0001343945,0.000149343],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07354103,0.00001520887,0.9231231,0.0003054188,0.001874973,0.0001987363,3.407238e-7,0.000312428,0.0006288074],"genre_scores_gemma":[0.8672244,5.876153e-7,0.1324682,0.00007342711,0.0001322585,0.000008509438,0.000002573705,0.000008707347,0.00008132192],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7936834,"threshold_uncertainty_score":0.8193598,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007174917290799207,"score_gpt":0.2491510403786483,"score_spread":0.2419761230878491,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}